Current PhD Students

Donglu is currently working on a joint model of cell-type-specific RNA and protein expressions in the human brain to shed light on biological discrepancies between cell-type-specific mRNA and protein levels. Donglu is also focusing on using machine learning models to better understand the interplay between metabolic pathways, histone modifications and gene expression across cell types. Her research interests also include studying protein conformational change and dynamics.

Cole Jensen is a computational biologist with an epidemiology, statistics, and evolutionary biology background. His research interests include developing computational evolutionary biology, population statistics, and graph-based approaches for studying B-cell biology.

Jason’s research focuses on leveraging genomics and biosensor/wearable data to better understand disorders and diseases related to the brain. Specifically, he uses novel deep learning and statistical approaches to find the underlying biological differences between various phenotypes.

Raghav’s research focuses on understanding Human Aging. Through his research Raghav is trying to answer critical questions such as “What are the biological systems and processes driving human aging?”, “How can we measure biological aging?”, “Can we reverse the processes driving Aging?” and “How does Aging give rise to diseases like Cancer, Diabetes, Alzheimer’s and more?”. To answer these questions, Raghav is building deep learning tools and techniques using multi-omic (Epigenetics, Transcriptomics, Proteomics, Metabolomics et al) and multi-modal data (Whole body and Organular Biomarkers, Tissue Omics and Single-Cell Omics).

Jeremy is interested in developing novel holistic computational methods that work with multi-omics datasets. Specifically, he is working on improving multi-omic data integration through the use of latent factor models.

Yaroslav is studying the molecular mechanisms behind organismal aging with the ultimate goal of developing strategies to modulate this universal process. He is especially interested in the role of somatic mutations in age-related dysregulation of gene expression and uses machine learning to better understand it.

Vimig is interested in clinical knowledge representation, NLP, and patient representations. He is currently working on a project in automated EHR data curation.

Junchen’s major interest is developing and applying computational methods to analyze high-dimensional transcriptomic data. He is also interested in tackling emerging sequencing protocol-oriented questions.  Currently, he is working on cell-interaction interpretations from single-cell RNA-sequencing data, and feature selection problems using novel deep learning methods.

Edel’s research is focused on developing a novel computational method capable of incorporating information from multiple forms of single-cell RNA sequencing in order to improve clustering and cell type annotation accuracy. This method will allow for deeper exploration of the host immune response at the cellular level.